论文标题
PNEL：基于指针网络的端到端实体，通过知识图链接
PNEL: Pointer Network based End-To-End Entity Linking over Knowledge Graphs
论文作者
论文摘要
问题回答系统通常被建模为由一系列步骤组成的管道。在这样的管道中，链接（EL）的实体通常是第一步。几种EL模型首先执行跨度检测，然后进行实体歧义。在此类模型中，从跨度检测阶段级联到以后的步骤，并导致总体准确性下降。此外，缺乏黄金实体在训练数据中跨度是跨度检测器训练的限制因素。因此，向端到端EL模型的运动开始，不涉及单独的跨度检测步骤。在这项工作中，我们通过应用流行的指针网络模型来提出一种新颖的方法来端到端EL，该模型可实现竞争性能。我们在Wikidata知识图上的三个数据集评估中证明了这一点。
Question Answering systems are generally modelled as a pipeline consisting of a sequence of steps. In such a pipeline, Entity Linking (EL) is often the first step. Several EL models first perform span detection and then entity disambiguation. In such models errors from the span detection phase cascade to later steps and result in a drop of overall accuracy. Moreover, lack of gold entity spans in training data is a limiting factor for span detector training. Hence the movement towards end-to-end EL models began where no separate span detection step is involved. In this work we present a novel approach to end-to-end EL by applying the popular Pointer Network model, which achieves competitive performance. We demonstrate this in our evaluation over three datasets on the Wikidata Knowledge Graph.
